Akim_Borbuev - Machine Learning Pathway

Certificates June 2020 Certificates Machine Learning Pipeline (NLP) Self-Assessments
1

Assessment 1

Things learned:

  • Technical: Web scraping, Text pre-processing, NLP
  • Tools: Github, Scrapy, BeautifulSoup, HTML
  • Soft skills: Collaboration and communication.

My three achievements

  • Learned how to use Scrapy and BeautifulSoup
  • Developed my first web crawler for data mining from the selected website
  • Performed data cleaning and exported to a csv/json files.

List of meeting/training attended

  • STEM-Casts: Overview of ML and project
  • STEM-Casts: A deep dive into Data Mining
  • Github webinar
  • Weekly team meeting on 6/1
  • Weekly team meeting on 6/8
  • Weekly team meeting on 6/15

Goals for upcoming week

  • Practice data cleaning and EDA
  • Learn more about text pre-processing
  • Learn more about NLP
2

Assessment 2

Things learned:

  • Technical: Data cleaning, Text pre-processing, NLP
  • Tools: nltk, gensim, scipy, BERT
  • Soft skills: Collaboration and teamwork.

My three achievements

  • Performed data cleaning and text preprocessing
  • Developed my first topic modelling program
  • Started applying BERT in text classification

List of meeting/training attended

  • NLP webinars
  • Weekly team meeting on 6/22

Goals for upcoming week

  • Finish text classifier using BERT
  • Continue learning more about NLP
  • Deploy and serve ML text classifier
3

Final Assessment

Things learned::

  1. Technical: Fine-tuning BERT Model
  2. Tools: Colab
  3. Soft Skills: Teamwork

My three achievements

  1. Learned BERT framework
  2. Fine-tuned BERT pre-trained model for text classification
  3. Expanded my knowledge about NLP

List of meeting/training attended

  1. Weekly team meeting on 6/29
  2. Weekly team meeting on 7/6

Goals for upcoming week

  1. Improve BERT text classifier
  2. Compare the results with other classifiers